© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13044
    Prev
    Next
    INDEX
    Explanations

    world of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othy
    -0.18
    меÑĢ
    -0.18
    åħ´ä¸ļ
    -0.18
    è¿Ļ个æĹ¶ä»£
    -0.17
    åľ¨è¿Ļ个
    -0.17
    igua
    -0.17
    _ws
    -0.17
    _fre
    -0.17
    æł·çļĦ
    -0.17
    带ä¸Ĭ
    -0.17
    POSITIVE LOGITS
    éĩĮ
    0.19
     Hoffman
    0.18
    æ°ĽåĽ´
    0.18
    åŃIJéĩĮ
    0.18
    è¡£æľį
    0.17
    fy
    0.17
    丰å¯Į
    0.17
    æµģ转
    0.16
    ä¸¥æł¼æī§è¡Į
    0.16
     заÑĤем
    0.16
    Activations Density 0.024%

    No Known Activations